A
Antonio Torralba
Researcher at Massachusetts Institute of Technology
Publications - 437
Citations - 105763
Antonio Torralba is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 119, co-authored 388 publications receiving 84607 citations. Previous affiliations of Antonio Torralba include Vassar College & Nvidia.
Papers
More filters
Journal ArticleDOI
Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos
TL;DR: In this article , a physics-driven diffusion model was proposed to synthesize high-fidelity impact sound for a silent video clip, where additional physics priors were used to guide the impact sound synthesis procedure.
MIT Open Access Articles Accidental Pinhole and Pinspeck Cameras
TL;DR: In this article , the authors identify and study two types of "accidental" images that can be formed in scenes: the first is an accidental pinhole camera image and the second is "inverse" camera image, formed by subtracting an image with a small occluder present from a reference image without the occloser.
Posted Content
Ambient Sound Provides Supervision for Visual Learning
Andrew Owens,Jiajun Wu,Josh H. McDermott,William T. Freeman,William T. Freeman,Antonio Torralba +5 more
TL;DR: In this paper, a convolutional neural network is trained to predict a summary of the sound associated with a video frame, and the network learns a representation that conveys information about objects and scenes.
Compositional Visual Generation with Composable Diffusion Models Supplementary
TL;DR: In this paper , the authors used a single 32GB GPU for both (750, iterations) and days (250, 000 iterations) of a GPU-based GPU-powered system.
Posted Content
What You Can Learn by Staring at a Blank Wall
Prafull Sharma,Miika Aittala,Yoav Y. Schechner,Antonio Torralba,Gregory W. Wornell,William T. Freeman,Frédo Durand +6 more
TL;DR: In this article, the authors present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room.